With the explosion of semantic web technologies, large amounts of OWL ontologies are common place. Conventional rule engines inevitably meet the bottleneck of computing performance and scalability. A cloud computing based SWRL distributed reasoning framework named CloudSWRL is proposed. Based on the Hadoop open-source framework and SWRL semantics, the storage schema for OWL ontologies is designed to implement efficient data retrieving from HBase. Some novel data models for SWRL rules and intermediate data are defined. At last, a MapReduce paradigm based distributed SWRL reasoning algorithm is proposed under DL-safe restriction. An experiment on a simulation environment shows our framework is more efficient and scalable than conventional rule engines when reasoning over large-scale of OWL data.